Author name: Ning Zhu

arXiv:2603.23766v2 Announce Type: replace
Abstract: Unsupervised medical anomaly detection is severely limited by the scarcity of normal training samples. Existing methods typically train dedicated models for each dataset or disease, requiring hundred…

arXiv:2603.23766v1 Announce Type: new
Abstract: Unsupervised medical anomaly detection is severely limited by the scarcity of normal training samples. Existing methods typically train dedicated models for each dataset or disease, requiring hundreds of…